ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation

Early intervention in tumors can greatly improve human survival rates. With the development of deep learning technology, automatic image segmentation has taken a prominent role in the field of medical image analysis. Manually segmenting kidneys on CT images is a tedious task, and due to the diversity of these images and varying technical skills of professionals, segmentation results can be inconsistent. To address this problem, a novel ASD-Net network is proposed in this paper for kidney and kidney tumor segmentation tasks. First, the proposed network employs newly designed Adaptive Spatial-channel Convolution Optimization (ASCO) blocks to capture anisotropic information in the images. Then, other newly designed blocks, i.e., Dense Dilated Enhancement Convolution (DDEC) blocks, are utilized to enhance feature propagation and reuse it across the network, thereby improving its segmentation accuracy. To allow the network to segment complex and small kidney tumors more effectively, the Atrous Spatial Pyramid Pooling (ASPP) module is incorporated in its middle layer. With its generalized pyramid feature, this module enables the network to better capture and understand context information at various scales within the images. In addition to this, the concurrent spatial and channel squeeze & excitation (scSE) attention mechanism is adopted to better comprehend and manage context information in the images. Additional encoding layers are also added to the base (U-Net) and connected to the original encoding layer through skip connections. The resultant enhanced U-Net structure allows for better extraction and merging of high-level and low-level features, further boosting the network's ability to restore segmentation details. In addition, the combined Binary Cross Entropy (BCE)-Dice loss is utilized as the network's loss function. Experiments, conducted on the KiTS19 dataset, demonstrate that the proposed ASD-Net network outperforms the existing segmentation networks according to all evaluation metrics used, except for recall in the case of kidney tumor segmentation, where it takes the second place after Attention-UNet.

DTONet a Lightweight Model for Melanoma Segmentation

With the further development of neural networks, automatic segmentation techniques for melanoma are becoming increasingly mature, especially under the conditions of abundant hardware resources. This allows for the accuracy of segmentation to be improved by increasing the complexity and computational capacity of the model. However, a new problem arises when it comes to actual applications, as there may not be the high-end hardware available, especially in hospitals and among the general public, who may have limited computing resources. In response to this situation, this paper proposes a lightweight deep learning network that can achieve high segmentation accuracy with minimal resource consumption. We introduce a network called DTONet (double-tailed octave network), which was specifically designed for this purpose. Its computational parameter count is only 30,859, which is 1/256th of the mainstream UNet model. Despite its reduced complexity, DTONet demonstrates superior performance in terms of accuracy, with an IOU improvement over other similar models. To validate the generalization capability of this model, we conducted tests on the PH2 dataset, and the results still outperformed existing models. Therefore, the proposed DTONet network exhibits excellent generalization ability and is sufficiently outstanding.

ResDAC-Net: a novel pancreas segmentation model utilizing residual double asymmetric spatial kernels

The pancreas not only is situated in a complex abdominal background but is also surrounded by other abdominal organs and adipose tissue, resulting in blurred organ boundaries. Accurate segmentation of pancreatic tissue is crucial for computer-aided diagnosis systems, as it can be used for surgical planning, navigation, and assessment of organs. In the light of this, the current paper proposes a novel Residual Double Asymmetric Convolution Network (ResDAC-Net) model. Firstly, newly designed ResDAC blocks are used to highlight pancreatic features. Secondly, the feature fusion between adjacent encoding layers fully utilizes the low-level and deep-level features extracted by the ResDAC blocks. Finally, parallel dilated convolutions are employed to increase the receptive field to capture multiscale spatial information. ResDAC-Net is highly compatible to the existing state-of-the-art models, according to three (out of four) evaluation metrics, including the two main ones used for segmentation performance evaluation (i.e., DSC and Jaccard index).

Grating-based x-ray dark-field CT for lung cancer diagnosis in mice

BACKGROUND

The low absorption of x-rays in lung tissue and the poor resolution of conventional computed tomography (CT) limits its use to detect lung disease. However, x-ray dark-field imaging can sense the scattered x-rays deflected by the structures being imaged. This technique can facilitate the detection of small alveolar lesions that would be difficult to detect with conventional CT. Therefore, it may provide an alternative imaging modality to diagnose lung disease at an early stage.

METHODS

Eight mice were inoculated with lung cancers simultaneously. Each time two mice were scanned using a grating-based dark-field CT on days 4, 8, 12, and 16 after the introduction of the cancer cells. The detectability index was calculated between nodules and healthy parenchyma for both attenuation and dark-field modalities. High-resolution micro-CT and pathological examinations were used to crosscheck and validate our results. Paired t-test was used for comparing the ability of dark-field and attenuation modalities in pulmonary nodule detection.

RESULTS

The nodules were shown as a signal decrease in the dark-field modality and a signal increase in the attenuation modality. The number of nodules increased from day 8 to day 16, indicating disease progression. The detectability indices of dark-field modality were higher than those of attenuation modality (p = 0.025).

CONCLUSIONS

Compared with the standard attenuation CT, the dark-field CT improved the detection of lung nodules.

RELEVANCE STATEMENT

Dark-field CT has a higher detectability index than conventional attenuation CT in lung nodule detection. This technique could improve the early diagnosis of lung cancer.

KEY POINTS

• Lung cancer progression was observed using x-ray dark-field CT. • Dark-field modality complements with attenuation modality in lung nodule detection. • Dark-field modality showed a detectability index higher than that attenuation in nodule detection.

DSP-KD: Dual-Stage Progressive Knowledge Distillation for Skin Disease Classification

The increasing global demand for skin disease diagnostics emphasizes the urgent need for advancements in AI-assisted diagnostic technologies for dermatoscopic images. In current practical medical systems, the primary challenge is balancing lightweight models with accurate image analysis to address constraints like limited storage and computational costs. While knowledge distillation methods hold immense potential in healthcare applications, related research on multi-class skin disease tasks is scarce. To bridge this gap, our study introduces an enhanced multi-source knowledge fusion distillation framework, termed DSP-KD, which improves knowledge transfer in a dual-stage progressive distillation approach to maximize mutual information between teacher and student representations. The experimental results highlight the superior performance of our distilled ShuffleNetV2 on both the ISIC2019 dataset and our private skin disorders dataset. Compared to other state-of-the-art distillation methods using diverse knowledge sources, the DSP-KD demonstrates remarkable effectiveness with a smaller computational burden.

Metallic Materials for Bone Repair

Repair of large bone defects caused by trauma or disease poses significant clinical challenges. Extensive research has focused on metallic materials for bone repair because of their favorable mechanical properties, biocompatibility, and manufacturing processes. Traditional metallic materials, such as stainless steel and titanium alloys, are widely used in clinics. Biodegradable metallic materials, such as iron, magnesium, and zinc alloys, are promising candidates for bone repair because of their ability to degrade over time. Emerging metallic materials, such as porous tantalum and bismuth alloys, have gained attention as bone implants owing to their bone affinity and multifunctionality. However, these metallic materials encounter many practical difficulties that require urgent improvement. This article systematically reviews and analyzes the metallic materials used for bone repair, providing a comprehensive overview of their morphology, mechanical properties, biocompatibility, and in vivo implantation. Furthermore, the strategies and efforts made to address the short-comings of metallic materials are summarized. Finally, the perspectives for the development of metallic materials to guide future research and advancements in clinical practice are identified.

Surgical strategies and outcomes for myocardial bridges coexisting with other cardiac conditions

BACKGROUND

Myocardial bridges are congenital coronary artery anomalies. There are still many controversies surrounding surgical treatment strategies for myocardial bridges combined with other heart disorders. The purpose of this study was to evaluate the surgical treatment strategies and outcomes in patients with these conditions.

METHODS

Between March 2004 and October 2021, our institution witnessed 77 patients diagnosed with myocardial bridging who underwent surgical intervention. According to the myocardial bridge and combined heart disorder, four groups were identified: 1. isolated LAD supra-arterial myotomy group, 2. LAD CABG and(or not) myotomy  group, 3. LAD supra-arterial myotomy and grafting of other branches group, and 4. LAD supra-arterial myotomy and other cardiac surgery group. The perioperative outcomes, symptoms, life quality, mortality, and major adverse cardiac events (MACEs) were analyzed.

RESULTS

There were no deaths during hospitalization and no rethoractomy for postoperative bleeding or major adverse cardiac events (MACEs). The follow-up period ranged from 2 months to 199.2 months (55.61 ± 10.21) months, the 10-year cumulative survival rates for the four groups of patients were 95.0%, 100%, 100% and 74.1%, and the 10-year freedom rates from the MACEs were 83.9%, 92.0%, 87.5% and 76.2%, respectively.

CONCLUSIONS

Supra-arterial myotomy is preferred in patients with isolated myocardial bridge, and acceptable results can be achieved by choosing supra-arterial myotomy in combination with CABG or other cardiac surgery simultaneously for patients with myocardial bridges and other heart disorders.

Evaluation of Early Diabetic Kidney Disease Using Ultrasound Localization Microscopy: A Feasibility Study

OBJECTIVE

The purpose of this study is to detect the hemodynamic changes of microvessels in the early stage of diabetic kidney disease (DKD) and to test the feasibility of ultrasound localization microscopy (ULM) in early diagnosis of DKD.

METHODS

In this study, streptozotocin (STZ) induced DKD rat model was used. Normal rats served as the control group. Conventional ultrasound, contrast-enhanced ultrasound (CEUS), and ULM data were collected and analyzed. The kidney cortex was divided into four segments, which are 0.25-0.5 mm (Segment 1), 0.5-0.75 mm (Segment 2), 0.75-1 mm (Segment 3), and 1-1.25 mm (Segment 4) away from the renal capsule, respectively. The mean blood flow velocities of arteries and veins in each segment were separately calculated, and also the velocity gradients and overall mean velocities of arteries and veins. Mann-Whitney U test was used for comparison of the data.

RESULTS

Quantitative results of microvessel velocity obtained by ULM show that the arterial velocity of Segments 2, 3, and 4, and the overall mean arterial velocity of the four segments in the DKD group are significantly lower than those in the normal group. The venous velocity of Segment 3 and the overall mean venous velocity of the four segments in the DKD group are higher than those in the normal group. The arterial velocity gradient in the DKD group is lower than that in the normal group.

CONCLUSION

ULM can visualize and quantify the blood flow and may be used for early diagnosis of DKD.

PneuNet: deep learning for COVID-19 pneumonia diagnosis on chest X-ray image analysis using Vision Transformer

A long-standing challenge in pneumonia diagnosis is recognizing the pathological lung texture, especially the ground-glass appearance pathological texture. One main difficulty lies in precisely extracting and recognizing the pathological features. The patients, especially those with mild symptoms, show very little difference in lung texture, neither conventional computer vision methods nor convolutional neural networks perform well on pneumonia diagnosis based on chest X-ray (CXR) images. In the meanwhile, the Coronavirus Disease 2019 (COVID-19) pandemic continues wreaking havoc around the world, where quick and accurate diagnosis backed by CXR images is in high demand. Rather than simply recognizing the patterns, extracting feature maps from the original CXR image is what we need in the classification process. Thus, we propose a Vision Transformer (VIT)-based model called PneuNet to make an accurate diagnosis backed by channel-based attention through X-ray images of the lung, where multi-head attention is applied on channel patches rather than feature patches. The techniques presented in this paper are oriented toward the medical application of deep neural networks and VIT. Extensive experiment results show that our method can reach 94.96% accuracy in the three-categories classification problem on the test set, which outperforms previous deep learning models.

Hepatic arterial infusion chemotherapy with or without lenvatinib for unresectable cholangiocarcinoma: a single-center retrospective study

Aim

The purpose of this study is to compare the efficacy and safety of hepatic arterial infusion chemotherapy (HAIC) of oxaliplatin, fluorouracil and leucovorin (FOLFOX) plus lenvatinib and FOLFOX-HAIC alone in patients with unresectable cholangiocarcinoma.

Patients & methods

Retrospective analysis of patients receiving FOLFOX-HAIC with or without lenvatinib.

Results

Forty-one patients were included, with 22 patients receiving HAIC alone and 19 patients receiving HAIC plus lenvatinib. Combination treatment significantly prolonged overall survival and progression-free survival compared with HAIC alone. Grade 1-2 adverse events were more frequent in the combination group but manageable. No severe AEs or treatment-related deaths were reported.

Conclusion

FOLFOX-HAIC plus lenvatinib has the potential to be a treatment option for unresectable cholangiocarcinoma.

Multimodal-based machine learning strategy for accurate and non-invasive prediction of intramedullary glioma grade and mutation status of molecular markers: a retrospective study

BACKGROUND

Determining the grade and molecular marker status of intramedullary gliomas is important for assessing treatment outcomes and prognosis. Invasive biopsy for pathology usually carries a high risk of tissue damage, especially to the spinal cord, and there are currently no non-invasive strategies to identify the pathological type of intramedullary gliomas. Therefore, this study aimed to develop a non-invasive machine learning model to assist doctors in identifying the intramedullary glioma grade and mutation status of molecular markers.

METHODS

A total of 461 patients from two institutions were included, and their sagittal (SAG) and transverse (TRA) T2-weighted magnetic resonance imaging scans and clinical data were acquired preoperatively. We employed a transformer-based deep learning model to automatically segment lesions in the SAG and TRA phases and extract their radiomics features. Different feature representations were fed into the proposed neural networks and compared with those of other mainstream models.

RESULTS

The dice similarity coefficients of the Swin transformer in the SAG and TRA phases were 0.8697 and 0.8738, respectively. The results demonstrated that the best performance was obtained in our proposed neural networks based on multimodal fusion (SAG-TRA-clinical) features. In the external validation cohort, the areas under the receiver operating characteristic curve for graded (WHO I-II or WHO III-IV), alpha thalassemia/mental retardation syndrome X-linked (ATRX) status, and tumor protein p53 (P53) status prediction tasks were 0.8431, 0.7622, and 0.7954, respectively.

CONCLUSIONS

This study reports a novel machine learning strategy that, for the first time, is based on multimodal features to predict the ATRX and P53 mutation status and grades of intramedullary gliomas. The generalized application of these models could non-invasively provide more tumor-specific pathological information for determining the treatment and prognosis of intramedullary gliomas.

Optical coherence tomography angiography with adaptive multi-time interval

Optical coherence tomography angiography (OCTA) can provide in vivo three-dimensional microvasculature information of bio-tissues, but it is sensitive to motion and time-consuming. To overcome these limitations, we propose an adaptive multiple time interval correlation mapping OCTA with a time-efficient scanning protocol and motion compensation algorithms. A spectral-domain OCT with a center wavelength of 850 nm, A-scan rate of 120 kHz and spatial resolution of 4.1 μm (axial) × 6.9 μm (lateral) is built to reconstruct the microvascular networks in the human arm. By adaptive optimization of the weights of different time interval B-scan angiograms, our novel OCTA technique achieves better performance with a visible vascular density increase of ~67% and a signal-to-noise ratio enhancement of ~11.6%.

Cerebral venous thrombosis with hyperhomocysteinemia due to loss of heterozygosity at methylenetetrahydrofolate reductase (MTHFR) locus: a case report

BACKGROUND

Loss of heterozygosity (LOH) at methylenetetrahydrofolate reductase (MTHFR) locus has been reported in tumor tissue. But the mutation was never reported in cerebral venous thrombosis (CVT) with hyperhomocysteinemia (HHcy) before.

CASE PRESENTATION

A 14-year-old girl was admitted with an intermittent headache and nausea for 2 months. The plasma homocysteine level was 77.2 µmol/L. Lumbar puncture revealed an intracranial pressure > 330 mmH2O. Cerebral MRI and MRV revealed superior sagittal sinus thrombosis. Whole-exome sequencing revealed LOH at Chr1:11836597-11,867,232 affects exons 10-21 of C1orf167, the entire MTHFR, and exons 1-2 of the CLCN6 gene. The normal allele was the c.665 C > T/677 C > T variant in MTHFR. The patient was treated with nadroparin for 2 weeks, followed by oral rivaroxaban. Supplemental folate and vitamins B12 and B6 were prescribed. One month later, she had no headache and the intracranial pressure had decreased to 215 mmH2O. MRI showed shrinkage of the thrombosis in the superior sagittal sinus, the degree of stenosis had significantly decreased.

CONCLUSIONS

Rare LOH at the MTHFR locus should be analyzed in CVT with HHcy. With anticoagulation treatment, the prognosis was good.

The role of altered lipid composition and distribution in liver fibrosis revealed by multimodal nonlinear optical microscopy

Intracellular lipid accumulation is commonly seen in fibrotic livers, but its exact role in liver fibrosis remains elusive. Here, we established a multimodal nonlinear optical microscopy to quantitatively map distribution of biomolecules in fibrotic livers. Our data revealed that unsaturated triglycerides were predominantly accumulated in central vein area during liver fibrosis but not in portal vein area. Moreover, the lipid homeostasis was remarkably dysregulated in the late-stage compared to the early-stage fibrosis, including increased unsaturated triglycerides with decreased lipid unsaturation degree and decreased membrane fluidity. Such alterations were likely due to up-regulated lipogenesis, desaturation, and peroxidation, which consequently led to endoplasmic reticulum stress and cell death. Inspiringly, injured hepatocyte could be rescued by remodeling lipid homeostasis via either supply of unsaturated fatty acids or enhancement of membrane fluidity. Collectively, our study improves current understanding of the role of lipid homeostasis in fibrosis and open opportunities for treatment.